Dr Yipeng Qin
BSc (Hons), PhD, FHEA
Uwch Ddarlithydd
Yr Ysgol Cyfrifiadureg a Gwybodeg
- QinY16@caerdydd.ac.uk
- +44 29208 75537
- Abacws, Ystafell 2.20, Ffordd Senghennydd, Cathays, Caerdydd, CF24 4AG
- Ar gael fel goruchwyliwr ôl-raddedig
Trosolwyg
Fi yw Arweinydd Grŵp Ymchwil Golwg Cyfrifiadurol yr adran ymchwil Cyfrifiadura Gweledol, ac Uwch Ddarlithydd (~Athro Cyswllt) yn yr Ysgol Cyfrifiadureg a Gwybodeg. Rwyf hefyd yn aelod o Goleg Adolygu Cymheiriaid EPSRC. Derbyniais fy PhD mewn Cyfrifiadureg gan y Ganolfan Genedlaethol ar gyfer Animeiddio Cyfrifiadurol (NCCA), Prifysgol Bournemouth, y DU yn 2017, a fy BSc mewn Peirianneg Drydanol o Brifysgol Shanghai Jiao Tong, Tsieina yn 2013.
Mae fy niddordebau ymchwil yn canolbwyntio ar ddysgu peirianyddol a'i gymwysiadau mewn gweledigaeth gyfrifiadurol, graffeg gyfrifiadurol, rhyngweithio dynol-cyfrifiadurol, ac ati. Mae fy ymchwil cyfredol yn troi o gwmpas y tair thema ganlynol: i) dadbocsio'r blwch du dysgu dwfn, ii) deallusrwydd artiffisial creadigol (AI) a iii) prototeipio dyfeisiau gwisgadwy ar gyfer monitro a dadansoddi symudiadau. Mae gen i ddiddordeb hefyd mewn pynciau cysylltiedig eraill fel segmentu semantig, addasu parth, dysgu lled-oruchwyliaeth, ac ati.
Mae croeso i bob math o gydweithio weithio!
Ar gyfer ymgeiswyr CSC: Mae Prifysgol Caerdydd yn elwa o bartneriaeth swyddogol gyda Chyngor Ysgoloriaethau Tsieina (CSC). Os oes gennych ddiddordeb mewn gwneud ymchwil gyda mi, cysylltwch â mi trwy e-bost cyn gynted â phosibl gan y gallai dyddiadau cau / camau ychwanegol fod yn berthnasol.
Cyhoeddiad
2024
- Chen, X. et al. 2024. Full-body human motion reconstruction with sparse joint tracking using flexible sensors. ACM Transactions on Multimedia Computing, Communications and Applications 20(2), article number: 44. (10.1145/3564700)
- Ren, T. et al. 2024. Diverse motion In-betweening from sparse keyframes with dual posture stitching. IEEE Transactions on Visualization and Computer Graphics (10.1109/TVCG.2024.3363457)
- Ying, E., Xiong, T., Zhu, G., Qiu, M., Qin, Y. and Guo, S. 2024. WristSketcher: Creating 2D dynamic sketches in AR with a sensing wristband. International Journal of Human-Computer Interaction (10.1080/10447318.2024.2301857)
- Zuo, C., Wang, Y., Zhan, L., Guo, S., Yi, X., Xu, F. and Qin, Y. 2024. Loose inertial poser: Motion capture with IMU-attached loose-wear jacket. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Seattle, USA, 17-21 June 2024.
- Liang, Y., Garg, B., Rosin, P. and Qin, Y. 2024. Deep generative model based rate-distortion for image downscaling assessment. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Seattle, USA, 17-21 June 2024.
- Chen, J., Qin, Y., Liu, L., Lu, J. and Li, G. 2024. NeRF-HuGS: Improved neural radiance fields in non-static scenes using heuristics-guided segmentation. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Seattle, USA, 17-21 June 2024.
- Ning, S., Wang, D., Qin, Y., Jin, Z., Wang, B. and Han, X. 2024. PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsign. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Seattle, USA, 17-21 June 2024.
2023
- Zhan, L. et al. 2023. TouchEditor: Interaction design and evaluation of a flexible touchpad for text editing of head-mounted displays in speech-unfriendly environments. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 7(4), pp. 1-29., article number: 198. (10.1145/3631454)
- Song, S., Liang, Y., Wu, J., Lai, Y. and Qin, Y. 2023. Feature proliferation — the "cancer" in StyleGAN and its treatments. Presented at: International Conference on Computer Vision (ICCV) 2023, Paris, France, October 1 - 6, 2023Proceedings of IEEE/CVF International Conference on Computer Vision. IEEE pp. 2360-2370., (10.1109/ICCV51070.2023.00224)
- Wang, K., Xu, X., Zheng, Y., Zhou, D., Guo, S., Qin, Y. and Guo, X. 2023. Computational design of wiring layout on tight suits with minimal motion resistance. Presented at: The 16th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia (SIGGRAPH ASIA 2023), Sydney, Australia, 12 - 15 December 2023.
- Fang, F. et al. 2023. Handwriting velcro: Endowing AR glasses with personalized and posture-adaptive text input using flexible touch sensor. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT) 6(4), pp. 1-31., article number: 163. (10.1145/3569461)
- Zhao, G., Li, G., Qin, Y. and Yu, Y. 2023. Improved distribution matching for dataset condensation. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, Vancouver, Canada, 18 - 22 June 2023.
- Huang, R., Lai, P., Qin, Y. and Li, G. 2023. Parametric implicit face representation for audio-driven facial reenactment. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, Vancouver, Canada, 18 - 22 June 2023.
- Zhou, W., Yue, G., Zhang, R., Qin, Y. and Liu, H. 2023. Reduced-reference quality assessment of point clouds via content-oriented saliency projection. IEEE Signal Processing Letters 30, pp. 354-358. (10.1109/LSP.2023.3264105)
- Zhao, X. et al. 2023. CUDAS: Distortion-aware saliency benchmark. IEEE Access 11, pp. 58025-58036. (10.1109/ACCESS.2023.3283344)
- Jones, O., Poudevigne-Durance, T. and Qin, Y. 2023. Synthesis of time-series with missing observations using generative adversarial networks. Presented at: 34th Panhellenic Statistics Conference, 19-22 May 2022. Greek Statistical Institute pp. 154-166.
- Zuo, C., Fang, J., Guo, S. and Qin, Y. 2023. Self-adaptive motion tracking against on-body displacement of flexible sensors. Presented at: Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, United States, 10 - 16 December 2023.
- Yan, Z., Wu, Y., Qin, Y., Han, X., Cui, S. and Li, G. 2023. Universal semi-supervised model adaptation via collaborative consistency training. Presented at: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024), Waikoloa, Hawaii, United States, 4 - 8 January 2024.
2022
- Poudevigne-Durance, T., Jones, O. D. and Qin, Y. 2022. MaWGAN: a generative adversarial network to create synthetic data from datasets with missing data. Electronics 11(6), article number: 837. (10.3390/electronics11060837)
- Yan, Z., Wu, Y., Li, G., Qin, Y., Han, X. and Cui, S. 2022. Multi-level consistency learning for semi-supervised domain adaptation. Presented at: 31st International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2022), Vienna, Austria, 23-29 July 2022.
- Liang, Y., Wu, J., Lai, Y. and Qin, Y. 2022. Exploring and exploiting hubness priors for high-quality GAN latent sampling. Presented at: The 39th International Conference on Machine Learning (ICML 2022), Baltimore, Maryland USA, 17-23 July 2022, Vol. 162.
- Chen, C., Shi, X., Qin, Y., Li, X., Yang, T., Han, X. and Guo, S. 2022. Real-world blind super-resolution via feature matching with implicit high-resolution priors. Presented at: the 30th ACM International Conference on Multimedia (ACMMM 2022), Lisbon, Portugal, 10 - 14 October 2022Proceedings of the 30th ACM International Conference on Multimedia (ACMMM 2022). ACM
- Yu, X., Tang, J., Qin, Y., Li, C., Han, X., Bao, L. and Cui, S. 2022. PVSeRF: joint pixel-, voxel- and surface-aligned radiance field for single-image novel view synthesis. Presented at: 30th ACM International Conference on Multimedia (ACMMM 2022), Lisbon, Portugal, 10 - 14 October 2022Proceedings ACMMM 2022 : 30th ACM International Conference on Multimedia. New York: ACM, (10.1145/3503161.3547893)
- Zhao, G., Li, G., Qin, Y., Liu, F. and Yu, Y. 2022. Centrality and consistency: two-stage clean samples identification for learning with instance-dependent noisy labels. Presented at: European Conference on Computer Vision (ECCV 2022), Tel Aviv, Israel, 23-27 October 2022.
2021
- Yan, Z., Yu, X., Qin, Y., Wu, Y., Han, X. and Cui, S. 2021. Pixel-level intra-domain adaptation for semantic segmentation. Presented at: ACM Multimedia 2021, Chengdu, China, 20-24 October 2021MM '21: Proceedings of the 29th ACM International Conference on Multimedia. ACM pp. 404-413., (10.1145/3474085.3475174)
- Zhu, Z. et al. 2021. Robust elbow angle prediction with aging soft sensors via output-level domain adaptation. IEEE Sensors Journal 21(20), pp. 22976-22984. (10.1109/JSEN.2021.3091004)
- Su, J., Gao, X., Qin, Y. and Guo, S. 2021. Correcting corrupted labels using mode dropping of ACGAN. Presented at: 15th International Symposium on Medical Information and Communication Technology (ISMICT 2021), Xiamen, China, 14-16 April 20212021 15th International Symposium on Medical Information and Communication Technology (ISMICT). IEEE pp. 98-103., (10.1109/ISMICT51748.2021.9434911)
- Chen, Z., Chen, X., Ma, Y., Guo, S., Qin, Y. and Liao, M. 2021. Human posture tracking with flexible sensors for motion recognition. Computer Animation and Virtual Worlds (10.1002/cav.1993)
2020
- Qin, Y., Mitra, N. and Wonka, P. 2020. How does Lipschitz regularization influence GAN training?. Presented at: 16th European Conference on Computer Vision (ECCV 2020), Glasgow, Scotland, 23-28 August 2020 Presented at Vevaldi, A. et al. eds.Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XVI. Lecture Notes in Computer Science Springer pp. 310-326., (10.1007/978-3-030-58517-4_19)
- Abdal, R., Qin, Y. and Wonka, P. 2020. Image2StyleGAN++: how to edit the embedded images?. Presented at: Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, Washington, USA, 16-18 June 2020.
- Zhu, P., Abdal, R., Qin, Y. and Wonka, P. 2020. SEAN: image synthesis with semantic region-adaptive normalization. Presented at: Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, Washington, USA, 14-19 June 2020.
2019
- Abdal, R., Qin, Y. and Wonka, P. 2019. Image2StyleGAN: How to embed images into the styleGAN latent space?. Presented at: International Conference on Computer Vision (ICCV) 2019, Seoul, South Korea, 27 October 2019 - 3 November 2019Proceedings of the International Conference on Computer Vision (ICCV) 2019. IEEE pp. 4431-4440., (\10.1109/ICCV.2019.00453)
2017
- Qin, Y., Yu, H. and Zhang, J. 2017. Fast and memory-efficient Voronoi diagram construction on triangle meshes. Computer Graphics Forum 36(5), pp. 93-104. (10.1111/cgf.13248)
2016
- Qin, Y., Han, X., Yu, H., Yu, Y. and Zhang, J. 2016. Fast and exact discrete geodesic computation based on triangle-oriented wavefront propagation. ACM Transactions on Graphics 35(4), article number: 125. (10.1145/2897824.2925930)
2015
- Yu, H., Qin, Y. and Zhang, J. J. 2015. Eigenspace-based surface completeness. Journal of Electronic Imaging 24(2), article number: 23037. (10.1117/1.JEI.24.2.023037)
Cynadleddau
- Zuo, C., Wang, Y., Zhan, L., Guo, S., Yi, X., Xu, F. and Qin, Y. 2024. Loose inertial poser: Motion capture with IMU-attached loose-wear jacket. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Seattle, USA, 17-21 June 2024.
- Liang, Y., Garg, B., Rosin, P. and Qin, Y. 2024. Deep generative model based rate-distortion for image downscaling assessment. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Seattle, USA, 17-21 June 2024.
- Chen, J., Qin, Y., Liu, L., Lu, J. and Li, G. 2024. NeRF-HuGS: Improved neural radiance fields in non-static scenes using heuristics-guided segmentation. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Seattle, USA, 17-21 June 2024.
- Ning, S., Wang, D., Qin, Y., Jin, Z., Wang, B. and Han, X. 2024. PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsign. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Seattle, USA, 17-21 June 2024.
- Song, S., Liang, Y., Wu, J., Lai, Y. and Qin, Y. 2023. Feature proliferation — the "cancer" in StyleGAN and its treatments. Presented at: International Conference on Computer Vision (ICCV) 2023, Paris, France, October 1 - 6, 2023Proceedings of IEEE/CVF International Conference on Computer Vision. IEEE pp. 2360-2370., (10.1109/ICCV51070.2023.00224)
- Wang, K., Xu, X., Zheng, Y., Zhou, D., Guo, S., Qin, Y. and Guo, X. 2023. Computational design of wiring layout on tight suits with minimal motion resistance. Presented at: The 16th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia (SIGGRAPH ASIA 2023), Sydney, Australia, 12 - 15 December 2023.
- Zhao, G., Li, G., Qin, Y. and Yu, Y. 2023. Improved distribution matching for dataset condensation. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, Vancouver, Canada, 18 - 22 June 2023.
- Huang, R., Lai, P., Qin, Y. and Li, G. 2023. Parametric implicit face representation for audio-driven facial reenactment. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, Vancouver, Canada, 18 - 22 June 2023.
- Jones, O., Poudevigne-Durance, T. and Qin, Y. 2023. Synthesis of time-series with missing observations using generative adversarial networks. Presented at: 34th Panhellenic Statistics Conference, 19-22 May 2022. Greek Statistical Institute pp. 154-166.
- Zuo, C., Fang, J., Guo, S. and Qin, Y. 2023. Self-adaptive motion tracking against on-body displacement of flexible sensors. Presented at: Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, United States, 10 - 16 December 2023.
- Yan, Z., Wu, Y., Qin, Y., Han, X., Cui, S. and Li, G. 2023. Universal semi-supervised model adaptation via collaborative consistency training. Presented at: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024), Waikoloa, Hawaii, United States, 4 - 8 January 2024.
- Yan, Z., Wu, Y., Li, G., Qin, Y., Han, X. and Cui, S. 2022. Multi-level consistency learning for semi-supervised domain adaptation. Presented at: 31st International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2022), Vienna, Austria, 23-29 July 2022.
- Liang, Y., Wu, J., Lai, Y. and Qin, Y. 2022. Exploring and exploiting hubness priors for high-quality GAN latent sampling. Presented at: The 39th International Conference on Machine Learning (ICML 2022), Baltimore, Maryland USA, 17-23 July 2022, Vol. 162.
- Chen, C., Shi, X., Qin, Y., Li, X., Yang, T., Han, X. and Guo, S. 2022. Real-world blind super-resolution via feature matching with implicit high-resolution priors. Presented at: the 30th ACM International Conference on Multimedia (ACMMM 2022), Lisbon, Portugal, 10 - 14 October 2022Proceedings of the 30th ACM International Conference on Multimedia (ACMMM 2022). ACM
- Yu, X., Tang, J., Qin, Y., Li, C., Han, X., Bao, L. and Cui, S. 2022. PVSeRF: joint pixel-, voxel- and surface-aligned radiance field for single-image novel view synthesis. Presented at: 30th ACM International Conference on Multimedia (ACMMM 2022), Lisbon, Portugal, 10 - 14 October 2022Proceedings ACMMM 2022 : 30th ACM International Conference on Multimedia. New York: ACM, (10.1145/3503161.3547893)
- Zhao, G., Li, G., Qin, Y., Liu, F. and Yu, Y. 2022. Centrality and consistency: two-stage clean samples identification for learning with instance-dependent noisy labels. Presented at: European Conference on Computer Vision (ECCV 2022), Tel Aviv, Israel, 23-27 October 2022.
- Yan, Z., Yu, X., Qin, Y., Wu, Y., Han, X. and Cui, S. 2021. Pixel-level intra-domain adaptation for semantic segmentation. Presented at: ACM Multimedia 2021, Chengdu, China, 20-24 October 2021MM '21: Proceedings of the 29th ACM International Conference on Multimedia. ACM pp. 404-413., (10.1145/3474085.3475174)
- Su, J., Gao, X., Qin, Y. and Guo, S. 2021. Correcting corrupted labels using mode dropping of ACGAN. Presented at: 15th International Symposium on Medical Information and Communication Technology (ISMICT 2021), Xiamen, China, 14-16 April 20212021 15th International Symposium on Medical Information and Communication Technology (ISMICT). IEEE pp. 98-103., (10.1109/ISMICT51748.2021.9434911)
- Qin, Y., Mitra, N. and Wonka, P. 2020. How does Lipschitz regularization influence GAN training?. Presented at: 16th European Conference on Computer Vision (ECCV 2020), Glasgow, Scotland, 23-28 August 2020 Presented at Vevaldi, A. et al. eds.Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XVI. Lecture Notes in Computer Science Springer pp. 310-326., (10.1007/978-3-030-58517-4_19)
- Abdal, R., Qin, Y. and Wonka, P. 2020. Image2StyleGAN++: how to edit the embedded images?. Presented at: Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, Washington, USA, 16-18 June 2020.
- Zhu, P., Abdal, R., Qin, Y. and Wonka, P. 2020. SEAN: image synthesis with semantic region-adaptive normalization. Presented at: Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, Washington, USA, 14-19 June 2020.
- Abdal, R., Qin, Y. and Wonka, P. 2019. Image2StyleGAN: How to embed images into the styleGAN latent space?. Presented at: International Conference on Computer Vision (ICCV) 2019, Seoul, South Korea, 27 October 2019 - 3 November 2019Proceedings of the International Conference on Computer Vision (ICCV) 2019. IEEE pp. 4431-4440., (\10.1109/ICCV.2019.00453)
Erthyglau
- Chen, X. et al. 2024. Full-body human motion reconstruction with sparse joint tracking using flexible sensors. ACM Transactions on Multimedia Computing, Communications and Applications 20(2), article number: 44. (10.1145/3564700)
- Ren, T. et al. 2024. Diverse motion In-betweening from sparse keyframes with dual posture stitching. IEEE Transactions on Visualization and Computer Graphics (10.1109/TVCG.2024.3363457)
- Ying, E., Xiong, T., Zhu, G., Qiu, M., Qin, Y. and Guo, S. 2024. WristSketcher: Creating 2D dynamic sketches in AR with a sensing wristband. International Journal of Human-Computer Interaction (10.1080/10447318.2024.2301857)
- Zhan, L. et al. 2023. TouchEditor: Interaction design and evaluation of a flexible touchpad for text editing of head-mounted displays in speech-unfriendly environments. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 7(4), pp. 1-29., article number: 198. (10.1145/3631454)
- Fang, F. et al. 2023. Handwriting velcro: Endowing AR glasses with personalized and posture-adaptive text input using flexible touch sensor. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT) 6(4), pp. 1-31., article number: 163. (10.1145/3569461)
- Zhou, W., Yue, G., Zhang, R., Qin, Y. and Liu, H. 2023. Reduced-reference quality assessment of point clouds via content-oriented saliency projection. IEEE Signal Processing Letters 30, pp. 354-358. (10.1109/LSP.2023.3264105)
- Zhao, X. et al. 2023. CUDAS: Distortion-aware saliency benchmark. IEEE Access 11, pp. 58025-58036. (10.1109/ACCESS.2023.3283344)
- Poudevigne-Durance, T., Jones, O. D. and Qin, Y. 2022. MaWGAN: a generative adversarial network to create synthetic data from datasets with missing data. Electronics 11(6), article number: 837. (10.3390/electronics11060837)
- Zhu, Z. et al. 2021. Robust elbow angle prediction with aging soft sensors via output-level domain adaptation. IEEE Sensors Journal 21(20), pp. 22976-22984. (10.1109/JSEN.2021.3091004)
- Chen, Z., Chen, X., Ma, Y., Guo, S., Qin, Y. and Liao, M. 2021. Human posture tracking with flexible sensors for motion recognition. Computer Animation and Virtual Worlds (10.1002/cav.1993)
- Qin, Y., Yu, H. and Zhang, J. 2017. Fast and memory-efficient Voronoi diagram construction on triangle meshes. Computer Graphics Forum 36(5), pp. 93-104. (10.1111/cgf.13248)
- Qin, Y., Han, X., Yu, H., Yu, Y. and Zhang, J. 2016. Fast and exact discrete geodesic computation based on triangle-oriented wavefront propagation. ACM Transactions on Graphics 35(4), article number: 125. (10.1145/2897824.2925930)
- Yu, H., Qin, Y. and Zhang, J. J. 2015. Eigenspace-based surface completeness. Journal of Electronic Imaging 24(2), article number: 23037. (10.1117/1.JEI.24.2.023037)
- Chen, X. et al. 2024. Full-body human motion reconstruction with sparse joint tracking using flexible sensors. ACM Transactions on Multimedia Computing, Communications and Applications 20(2), article number: 44. (10.1145/3564700)
- Ren, T. et al. 2024. Diverse motion In-betweening from sparse keyframes with dual posture stitching. IEEE Transactions on Visualization and Computer Graphics (10.1109/TVCG.2024.3363457)
- Ying, E., Xiong, T., Zhu, G., Qiu, M., Qin, Y. and Guo, S. 2024. WristSketcher: Creating 2D dynamic sketches in AR with a sensing wristband. International Journal of Human-Computer Interaction (10.1080/10447318.2024.2301857)
- Zuo, C., Wang, Y., Zhan, L., Guo, S., Yi, X., Xu, F. and Qin, Y. 2024. Loose inertial poser: Motion capture with IMU-attached loose-wear jacket. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Seattle, USA, 17-21 June 2024.
- Liang, Y., Garg, B., Rosin, P. and Qin, Y. 2024. Deep generative model based rate-distortion for image downscaling assessment. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Seattle, USA, 17-21 June 2024.
- Zhan, L. et al. 2023. TouchEditor: Interaction design and evaluation of a flexible touchpad for text editing of head-mounted displays in speech-unfriendly environments. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 7(4), pp. 1-29., article number: 198. (10.1145/3631454)
- Song, S., Liang, Y., Wu, J., Lai, Y. and Qin, Y. 2023. Feature proliferation — the "cancer" in StyleGAN and its treatments. Presented at: International Conference on Computer Vision (ICCV) 2023, Paris, France, October 1 - 6, 2023Proceedings of IEEE/CVF International Conference on Computer Vision. IEEE pp. 2360-2370., (10.1109/ICCV51070.2023.00224)
- Wang, K., Xu, X., Zheng, Y., Zhou, D., Guo, S., Qin, Y. and Guo, X. 2023. Computational design of wiring layout on tight suits with minimal motion resistance. Presented at: The 16th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia (SIGGRAPH ASIA 2023), Sydney, Australia, 12 - 15 December 2023.
- Fang, F. et al. 2023. Handwriting velcro: Endowing AR glasses with personalized and posture-adaptive text input using flexible touch sensor. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT) 6(4), pp. 1-31., article number: 163. (10.1145/3569461)
- Zhao, G., Li, G., Qin, Y. and Yu, Y. 2023. Improved distribution matching for dataset condensation. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, Vancouver, Canada, 18 - 22 June 2023.
- Huang, R., Lai, P., Qin, Y. and Li, G. 2023. Parametric implicit face representation for audio-driven facial reenactment. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, Vancouver, Canada, 18 - 22 June 2023.
- Zuo, C., Fang, J., Guo, S. and Qin, Y. 2023. Self-adaptive motion tracking against on-body displacement of flexible sensors. Presented at: Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, United States, 10 - 16 December 2023.
- Yan, Z., Wu, Y., Qin, Y., Han, X., Cui, S. and Li, G. 2023. Universal semi-supervised model adaptation via collaborative consistency training. Presented at: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024), Waikoloa, Hawaii, United States, 4 - 8 January 2024.
- Yan, Z., Wu, Y., Li, G., Qin, Y., Han, X. and Cui, S. 2022. Multi-level consistency learning for semi-supervised domain adaptation. Presented at: 31st International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2022), Vienna, Austria, 23-29 July 2022.
- Liang, Y., Wu, J., Lai, Y. and Qin, Y. 2022. Exploring and exploiting hubness priors for high-quality GAN latent sampling. Presented at: The 39th International Conference on Machine Learning (ICML 2022), Baltimore, Maryland USA, 17-23 July 2022, Vol. 162.
- Chen, C., Shi, X., Qin, Y., Li, X., Yang, T., Han, X. and Guo, S. 2022. Real-world blind super-resolution via feature matching with implicit high-resolution priors. Presented at: the 30th ACM International Conference on Multimedia (ACMMM 2022), Lisbon, Portugal, 10 - 14 October 2022Proceedings of the 30th ACM International Conference on Multimedia (ACMMM 2022). ACM
- Yu, X., Tang, J., Qin, Y., Li, C., Han, X., Bao, L. and Cui, S. 2022. PVSeRF: joint pixel-, voxel- and surface-aligned radiance field for single-image novel view synthesis. Presented at: 30th ACM International Conference on Multimedia (ACMMM 2022), Lisbon, Portugal, 10 - 14 October 2022Proceedings ACMMM 2022 : 30th ACM International Conference on Multimedia. New York: ACM, (10.1145/3503161.3547893)
- Zhao, G., Li, G., Qin, Y., Liu, F. and Yu, Y. 2022. Centrality and consistency: two-stage clean samples identification for learning with instance-dependent noisy labels. Presented at: European Conference on Computer Vision (ECCV 2022), Tel Aviv, Israel, 23-27 October 2022.
- Yan, Z., Yu, X., Qin, Y., Wu, Y., Han, X. and Cui, S. 2021. Pixel-level intra-domain adaptation for semantic segmentation. Presented at: ACM Multimedia 2021, Chengdu, China, 20-24 October 2021MM '21: Proceedings of the 29th ACM International Conference on Multimedia. ACM pp. 404-413., (10.1145/3474085.3475174)
- Zhu, Z. et al. 2021. Robust elbow angle prediction with aging soft sensors via output-level domain adaptation. IEEE Sensors Journal 21(20), pp. 22976-22984. (10.1109/JSEN.2021.3091004)
- Chen, Z., Chen, X., Ma, Y., Guo, S., Qin, Y. and Liao, M. 2021. Human posture tracking with flexible sensors for motion recognition. Computer Animation and Virtual Worlds (10.1002/cav.1993)
- Qin, Y., Mitra, N. and Wonka, P. 2020. How does Lipschitz regularization influence GAN training?. Presented at: 16th European Conference on Computer Vision (ECCV 2020), Glasgow, Scotland, 23-28 August 2020 Presented at Vevaldi, A. et al. eds.Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XVI. Lecture Notes in Computer Science Springer pp. 310-326., (10.1007/978-3-030-58517-4_19)
- Abdal, R., Qin, Y. and Wonka, P. 2020. Image2StyleGAN++: how to edit the embedded images?. Presented at: Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, Washington, USA, 16-18 June 2020.
- Zhu, P., Abdal, R., Qin, Y. and Wonka, P. 2020. SEAN: image synthesis with semantic region-adaptive normalization. Presented at: Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, Washington, USA, 14-19 June 2020.
- Abdal, R., Qin, Y. and Wonka, P. 2019. Image2StyleGAN: How to embed images into the styleGAN latent space?. Presented at: International Conference on Computer Vision (ICCV) 2019, Seoul, South Korea, 27 October 2019 - 3 November 2019Proceedings of the International Conference on Computer Vision (ICCV) 2019. IEEE pp. 4431-4440., (\10.1109/ICCV.2019.00453)
- Qin, Y., Yu, H. and Zhang, J. 2017. Fast and memory-efficient Voronoi diagram construction on triangle meshes. Computer Graphics Forum 36(5), pp. 93-104. (10.1111/cgf.13248)
- Qin, Y., Han, X., Yu, H., Yu, Y. and Zhang, J. 2016. Fast and exact discrete geodesic computation based on triangle-oriented wavefront propagation. ACM Transactions on Graphics 35(4), article number: 125. (10.1145/2897824.2925930)
Ymchwil
Mae fy niddordebau ymchwil yn canolbwyntio ar ddysgu peiriant (ML) a'i gymwysiadau mewn golwg cyfrifiadurol (CV), graffeg gyfrifiadurol (CG), rhyngweithio dynol-cyfrifiadurol (HCI), ac ati. Mae fy ymchwil presennol yn ymwneud â'r tair thema ganlynol:
- Dadbocsio'r blwch du dysgu dwfn, sy'n ceisio deall deinameg hyfforddi amrywiol rwydweithiau niwral dwfn, e.e. Rhwydweithiau Gwrthwynebul Geneerative (GANs).
- Deallusrwydd Artiffisial Creadigol (AI), gan gynnwys gwrthdroad GAN, datodiad delwedd rhanbarth-ddoeth ar gyfer synthesis / trin delwedd amrywiol a rheolaethol, ac ati.
- Prototeipio dyfeisiau gwisgadwy ar gyfer monitro a dadansoddi symudiadau, sy'n anelu at fodelu'r berthynas rhwng signalau synhwyrydd a symudiad dynol gan ddefnyddio dysgu peiriant. Mae hwn yn ymchwil gydweithredol gyda'r Athro Shihui Guo o Brifysgol Xiamen, Tsieina.
Mae gen i ddiddordeb hefyd mewn pynciau cysylltiedig eraill fel segmentu semantig, addasu parth, dysgu lled-oruchwyliaeth, ac ati.
Prosiectau cyfredol
- Her AI Cynhyrchiol, £44,940, Co-I, Airbus Endeavr, Rhif 526236, Mai 2024 - Ionawr 2025
- Datblygu Map Ffordd – Creu Personas AI Chattable ar gyfer Amgueddfeydd ac Archifau, £4,000, PI®, Cyllid Seedcorn Sefydliad Arloesi Trawsnewid Digidol (DTII), Na. DTIIR3SC04, Ebrill 2024 - Awst 2024
- Chwyldroi Profiadau Ymwelwyr o Dreftadaeth Ddiwylliannol: Rhyddhau Pŵer Avatars Chattable wedi'u Pweru gan AI mewn Arddangosfeydd Rhyngweithiol, £15,000, PI, Cyfrif Cyflymu Effaith Cysonedig UKRI (IAA), Rhif 521632 (525436), Tachwedd 2023 - Mai 2024
- Charting New Frontiers: Astudiaeth Alldaith a Pheilot Archwiliol ar Chattable Virtual Avatars, Datgelu Dimensiynau Moesegol a Chymdeithasol mewn Cyflenwi Cynnwys, £ 5,000, PI, GW4 Cyllid Hadau Crucible 2023, Na. Cru23_01, Medi 2023 - Maw 2024
- Prototeipio Dillad Clyfar ar gyfer Monitro a Dadansoddi Cynnig ar lefel Poblogaeth, £12,000, PI, Cyfnewidiadau Rhyngwladol y Gymdeithas Frenhinol 2021 Cyfran Cost (NSFC), Na. IEC \NSFC\211022, Maw 2022 - Maw 2024
- Datgelu "Greddfau" Modelau Geneteg Dwfn ar gyfer Creu Cynnwys Gweledol Deg a Diduedd, tua £72,922, Prif Oruchwyliwr, EPSRC DTP, Na. EP/T517951/1 (2599521), Hydref 2021 - Maw 2025
Prosiectau blaenorol
- Optimeiddio Cynllun Synhwyrydd ar gyfer Ailadeiladu Siâp Corff 3D, £3,200, PI, Cyllid Cydweithio Ymchwil Prifysgol Caerdydd-Xiamen, Jul 2020 - Awst 2020
Gweithgareddau/Digwyddiadau
- [Digwyddiad Ymylol AI DU 2024] Past Meets Future: Can AI Personas Dod â Ffigurau Hanesyddol yn Fyw?, a drefnwyd gan Dr. Yipeng Qin, Mawrth 27, 2024
- Gweithdy Prifysgol Caerdydd a'r Ymddiriedolaeth Genedlaethol ar AI Avatars, wedi'i gyd-drefnu gan Dr Daniel Finnegan a Dr. Yipeng Qin, Mawrth 13, 2024
- Chattable Virtual Avatars ar gyfer Gweithdy Amgueddfa ac Archifau, a gyd-drefnwyd gan Dr Barbara Caddick o Brifysgol Bryste a Dr. Yipeng Qin, Mawrth 11, 2024.
Addysgu
Addysgu modiwlaidd
- 2021/22 - nawr, CMT307 Dysgu Peiriant Cymhwysol
- 2021/22 - nawr, CMT316 Cymwysiadau Dysgu Peiriant: Prosesu Iaith Naturiol / Gweledigaeth Gyfrifiadurol
- 2019/20 - nawr, CM1205 Architecture and Operating Systems, Arweinydd Modiwl
Rôl weinyddol
- 2020.10 - nawr, Arweinydd Rhaglen PGT (COMSC) MSc Gwyddor Data a Dadansoddeg ac MSc Dadansoddi Data ar gyfer Llywodraeth
- 2024.04 - nawr, Tiwtor Derbyn PGT
Dyfarniadau
- Cydweithrediad Dysgu ac Addysgu'r Flwyddyn (Enwebiad)
- Gwobrau Cyfoethogi Bywyd Myfyrwyr (ESLAs) 2024
- GAN: Prifysgol Caerdydd ac Undeb Myfyrwyr Caerdydd (CUSU)
- Hyrwyddwr Cydraddoldeb, Amrywiaeth a Chynhwysiant (Enwebiad)
- Gwobrau Cyfoethogi Bywyd Myfyrwyr (ESLAs) 2024
- GAN: Prifysgol Caerdydd ac Undeb Myfyrwyr Caerdydd (CUSU)
Bywgraffiad
Addysg a Chymwysterau
- 2017: PhD mewn Cyfrifiadureg, Canolfan Genedlaethol ar gyfer Animeiddio Cyfrifiadurol, Prifysgol Bournemouth, UK
- 2013: BEng mewn Peirianneg Drydanol, Prifysgol Shanghai Jiao Tong, Tsieina
Trosolwg gyrfa
- 2023 - presennol: Uwch Ddarlithydd, Prifysgol Caerdydd, UK
- 2019 - 2023: Darlithydd, Prifysgol Caerdydd, DU
- 2017 - 2019: Cymrawd Ymchwil Ôl-ddoethurol, Canolfan Cyfrifiadura Gweledol, Brenin Abdullah Prifysgol Gwyddoniaeth a Thechnoleg, Saudi Arabia
Anrhydeddau a dyfarniadau
- Cydweithrediad Dysgu ac Addysgu'r Flwyddyn (Enwebiad)
- Gwobrau Cyfoethogi Bywyd Myfyrwyr (ESLAs) 2024
- GAN: Prifysgol Caerdydd ac Undeb Myfyrwyr Caerdydd (CUSU)
- Hyrwyddwr Cydraddoldeb, Amrywiaeth a Chynhwysiant (Enwebiad)
- Gwobrau Cyfoethogi Bywyd Myfyrwyr (ESLAs) 2024
- GAN: Prifysgol Caerdydd ac Undeb Myfyrwyr Caerdydd (CUSU)
Aelodaethau proffesiynol
- Coleg Adolygu Cymheiriaid EPSRC
- Aelod o ACM SIGGRAPH, Sefydliad Golwg Cyfrifiadurol (CVF), AsiaGraphics
- Cymrodoriaeth yr AAU
- Rhwydwaith Ymchwilydd Gyrfa Cynnar yr Academi Brydeinig
- Dyniaethau a Gwyddor Data Grŵp Diddordeb Arbennig @ Sefydliad Alan Turing
Safleoedd academaidd blaenorol
- 2023 - presennol: Uwch Ddarlithydd, Prifysgol Caerdydd, UK
- 2019 - 2023: Darlithydd, Prifysgol Caerdydd, DU
- 2017 - 2019: Cymrawd Ymchwil Ôl-ddoethurol, Canolfan Cyfrifiadura Gweledol, Brenin Abdullah Prifysgol Gwyddoniaeth a Thechnoleg, Saudi Arabia
Pwyllgorau ac adolygu
- Cadeirydd Ardal: ICML 2024
- Adolygydd Grant:
- Coleg Adolygu Cymheiriaid EPSRC
- Turing AI Cymrodoriaethau Ymchwilwyr sy'n Arwain y Byd
- EPSRC
- Rhaglen Ariannu Ychwanegol EPSRC ar gyfer Gwyddoniaeth Fathemategol
- Gweithredu Ymchwil ar y Cyd Gwlad Belg (CRAs)
- Adolygydd Cyfnodolyn:
- Trafodion IEEE ar Ddadansoddiad Patrymau a Chudd-wybodaeth Peiriant (TPAMI)
- ACM Trafodion ar Graffeg (TOG)
- Trafodion IEEE ar Brosesu Delweddau (TIP)
- Trafodion IEEE ar Ddelweddu a Graffeg Cyfrifiadurol (TVCG)
- Fforwm Graffeg Cyfrifiadurol (CGF)
- Cydnabod Patrwm
- Niwrogyfrifiadura
- Cyfrifiaduron a Graffeg
- Mynediad IEEE
- Delwedd a Chyfrifiadura Gweledigaeth
- Ffiniau mewn Delweddu
- Pwyllgor Rhaglen Cynhadledd (PC) Aelod / Adolygydd:
- ACM SIGGRAPH
- ACM SIGGRAPH Asia
- CVPR
- ICCV
- ECCV
- NeurIPS
- ICLR
- ICML
- AAAI
- ACM MM
- Eurographics
- Graffeg Môr Tawel
- BMVC
- ACCV
- CVM
- CGI
- CASA
- IJCNN
- Adolygydd Llyfrau: Gwasg CRC/Taylor a Francis Group
Meysydd goruchwyliaeth
Mae gen i ddiddordeb mewn goruchwylio myfyrwyr PhD ym meysydd:
- AI ar gyfer Modelu Geneteg
- Synthesis Delwedd a Thrin
- ML/AI dehongladwy ar gyfer Cynhyrchu Cynnwys Gweledol
- Rhagfarn a thegwch mewn AI
- Prosesu geometreg 3D
Ar gyfer ymgeiswyr CSC: Mae Prifysgol Caerdydd yn elwa o bartneriaeth swyddogol gyda Chyngor Ysgoloriaethau Tsieina (CSC). Os oes gennych ddiddordeb mewn gwneud ymchwil gyda mi, cysylltwch â mi trwy e-bost cyn gynted â phosibl gan y gallai dyddiadau cau / camau ychwanegol fod yn berthnasol.
Goruchwylio PhD Cyfredol
- Stephen Miles (2021/07 - nawr) - Adfer Delwedd gyda Dysgu Dwfn (Rhan-amser).
- Yuanbang Liang (2021/10 - nawr) - Datgelu "greddf" Modelau Genetig Dwfn ar gyfer Creu Cynnwys Gweledol Deg a Diduedd (EPSRC DTP).
- Cân Shuang (2021/10 - nawr) - Rhwydwaith Amcangyfrif Dyfnder Nofel ar gyfer Pwytho Delwedd (CSC).
- Jinqi Wang (2022/10 - nawr) - Creu Cynnwys Anime seiliedig ar AI
- Zhuoling Jiang (2024/01 - nawr) - NPCs sy'n cael eu gyrru gan AI ar gyfer Hapchwarae Next-Generation (a ariennir gan yr Ysgol)
Cyd-oruchwylio
- Xin Zhao (2019/10 - yn awr) - Rhagfynegiad Sylwgar Llygaid gan y Gweithwyr Meddygol Proffesiynol yn y Ddelwedd Feddygol (cyd-oruchwylio Dr. Hantao Liu).
- Thomas Poudevigne-Durance (2019/10 - yn awr) - Rhwydweithiau Gwrthdroadol Cynhyrchiol ar gyfer Ehangu Digwyddiad Prin (cyd-oruchwylir gyda'r Athro Owen Jones, Ysgol Mathemateg).
- Hateef Alshewaier (2021/04 - nawr) - Dulliau Ensemble ar gyfer Dosbarthiad Data Amlgyfrwng (wedi'i oruchwylio ar y cyd â Dr. Xianfang Sun).
- Ebtihal Alwadee (2021/10 - nawr) - Dosbarthiad Rhwydwaith Niwral Down-Adaptive Adaptive ar gyfer Canfod Tiwmor yr Ymennydd O Ddelweddau Ymennydd Mri (cyd-oruchwylio gyda Dr. Frank Langbein a Dr. Xianfang Sun).
- Nada Saad M Alharbi (2023/10 - nawr) - Canfod Anhwylder Sbectrwm Awtistiaeth Defnyddio Dysgu Atgyfnerthu Dwfn (wedi'i oruchwylio ar y cyd â Dr. Xianfang Sun).
- Yang Li (2023/10 - nawr) - Modelau Geneerative ar gyfer Dylunio Ffasâd Pensaernïol (cyd-oruchwylir gyda Dr. Bailin Deng a'r Athro Wassim Jabi).
Goruchwyliaeth gyfredol
Shuang Song
Arddangoswr Graddedig
Jinqi Wang
Myfyriwr ymchwil
Zhuoling Jiang
Myfyriwr ymchwil
Stephen Miles
Myfyriwr ymchwil
Themâu ymchwil
Arbenigeddau
- Deallusrwydd artiffisial
- Graffeg cyfrifiadurol
- Golwg cyfrifiadurol
- Dysgu peirianyddol
- Rhyngweithio Cyfrifiadur Dynol